X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=treegroupscommand.cpp;h=626659501a531db80f5193bef33e88793414a874;hb=d04f948b1a2a1a2984fc4a45d04403b8c121c5bc;hp=e8f68e7f34c52258e480bd8e6f369a200734df1f;hpb=315e38cf393c82be238da5b32574f225a020d25c;p=mothur.git diff --git a/treegroupscommand.cpp b/treegroupscommand.cpp index e8f68e7..6266595 100644 --- a/treegroupscommand.cpp +++ b/treegroupscommand.cpp @@ -19,10 +19,58 @@ #include "sharedmorisitahorn.h" #include "sharedbraycurtis.h" - +//********************************************************************************************************************** +vector TreeGroupCommand::getValidParameters(){ + try { + string Array[] = {"label","calc","groups", "phylip", "column", "name", "precision","cutoff","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "TreeGroupCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +TreeGroupCommand::TreeGroupCommand(){ + try { + abort = true; + globaldata = GlobalData::getInstance(); + //initialize outputTypes + vector tempOutNames; + outputTypes["tree"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "TreeGroupCommand", "TreeGroupCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector TreeGroupCommand::getRequiredParameters(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "TreeGroupCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector TreeGroupCommand::getRequiredFiles(){ + try { + string Array[] = {"phylip","column","shared","or"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "TreeGroupCommand", "getRequiredFiles"); + exit(1); + } +} //********************************************************************************************************************** -TreeGroupCommand::TreeGroupCommand(string option){ +TreeGroupCommand::TreeGroupCommand(string option) { try { globaldata = GlobalData::getInstance(); abort = false; @@ -50,6 +98,10 @@ TreeGroupCommand::TreeGroupCommand(string option){ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["tree"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } @@ -58,7 +110,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ it = parameters.find("phylip"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["phylip"] = inputDir + it->second; } } @@ -66,7 +118,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ it = parameters.find("column"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["column"] = inputDir + it->second; } } @@ -74,7 +126,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ it = parameters.find("name"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["name"] = inputDir + it->second; } } @@ -86,12 +138,12 @@ TreeGroupCommand::TreeGroupCommand(string option){ phylipfile = validParameter.validFile(parameters, "phylip", true); if (phylipfile == "not open") { abort = true; } else if (phylipfile == "not found") { phylipfile = ""; } - else { format = "phylip"; globaldata->setPhylipFile(phylipfile); } + else { globaldata->newRead(); format = "phylip"; globaldata->setPhylipFile(phylipfile); } columnfile = validParameter.validFile(parameters, "column", true); if (columnfile == "not open") { abort = true; } else if (columnfile == "not found") { columnfile = ""; } - else { format = "column"; globaldata->setColumnFile(columnfile); } + else { globaldata->newRead(); format = "column"; globaldata->setColumnFile(columnfile); } namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { abort = true; } @@ -99,11 +151,11 @@ TreeGroupCommand::TreeGroupCommand(string option){ else { globaldata->setNameFile(namefile); } //error checking on files - if ((globaldata->getSharedFile() == "") && ((phylipfile == "") && (columnfile == ""))) { mothurOut("You must run the read.otu command or provide a distance file before running the tree.shared command."); mothurOutEndLine(); abort = true; } - else if ((phylipfile != "") && (columnfile != "")) { mothurOut("When running the tree.shared command with a distance file you may not use both the column and the phylip parameters."); mothurOutEndLine(); abort = true; } + if ((globaldata->getSharedFile() == "") && ((phylipfile == "") && (columnfile == ""))) { m->mothurOut("You must run the read.otu command or provide a distance file before running the tree.shared command."); m->mothurOutEndLine(); abort = true; } + else if ((phylipfile != "") && (columnfile != "")) { m->mothurOut("When running the tree.shared command with a distance file you may not use both the column and the phylip parameters."); m->mothurOutEndLine(); abort = true; } if (columnfile != "") { - if (namefile == "") { mothurOut("You need to provide a namefile if you are going to use the column format."); mothurOutEndLine(); abort = true; } + if (namefile == "") { m->mothurOut("You need to provide a namefile if you are going to use the column format."); m->mothurOutEndLine(); abort = true; } } //check for optional parameter and set defaults @@ -111,7 +163,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } else { - if(label != "all") { splitAtDash(label, labels); allLines = 0; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } @@ -124,7 +176,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } else { - splitAtDash(groups, Groups); + m->splitAtDash(groups, Groups); globaldata->Groups = Groups; } @@ -133,7 +185,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ else { if (calc == "default") { calc = "jclass-thetayc"; } } - splitAtDash(calc, Estimators); + m->splitAtDash(calc, Estimators); string temp; temp = validParameter.validFile(parameters, "precision", false); if (temp == "not found") { temp = "100"; } @@ -146,7 +198,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; - outputDir += hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it + outputDir += m->hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it } @@ -187,7 +239,7 @@ TreeGroupCommand::TreeGroupCommand(string option){ } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "TreeGroupCommand"); + m->errorOut(e, "TreeGroupCommand", "TreeGroupCommand"); exit(1); } } @@ -196,25 +248,25 @@ TreeGroupCommand::TreeGroupCommand(string option){ void TreeGroupCommand::help(){ try { - mothurOut("The tree.shared command creates a .tre to represent the similiarity between groups or sequences.\n"); - mothurOut("The tree.shared command can only be executed after a successful read.otu command or by providing a distance file.\n"); - mothurOut("The tree.shared command parameters are groups, calc, phylip, column, name, cutoff, precision and label.\n"); - mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like included used.\n"); - mothurOut("The group names are separated by dashes. The label allow you to select what distance levels you would like trees created for, and are also separated by dashes.\n"); - mothurOut("The phylip or column parameter are required if you do not run the read.otu command first, and only one may be used. If you use a column file the name filename is required. \n"); - mothurOut("If you do not provide a cutoff value 10.00 is assumed. If you do not provide a precision value then 100 is assumed.\n"); - mothurOut("The tree.shared command should be in the following format: tree.shared(groups=yourGroups, calc=yourCalcs, label=yourLabels).\n"); - mothurOut("Example tree.shared(groups=A-B-C, calc=jabund-sorabund).\n"); - mothurOut("The default value for groups is all the groups in your groupfile.\n"); - mothurOut("The default value for calc is jclass-thetayc.\n"); - mothurOut("The tree.shared command outputs a .tre file for each calculator you specify at each distance you choose.\n"); + m->mothurOut("The tree.shared command creates a .tre to represent the similiarity between groups or sequences.\n"); + m->mothurOut("The tree.shared command can only be executed after a successful read.otu command or by providing a distance file.\n"); + m->mothurOut("The tree.shared command parameters are groups, calc, phylip, column, name, cutoff, precision and label.\n"); + m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like included used.\n"); + m->mothurOut("The group names are separated by dashes. The label allow you to select what distance levels you would like trees created for, and are also separated by dashes.\n"); + m->mothurOut("The phylip or column parameter are required if you do not run the read.otu command first, and only one may be used. If you use a column file the name filename is required. \n"); + m->mothurOut("If you do not provide a cutoff value 10.00 is assumed. If you do not provide a precision value then 100 is assumed.\n"); + m->mothurOut("The tree.shared command should be in the following format: tree.shared(groups=yourGroups, calc=yourCalcs, label=yourLabels).\n"); + m->mothurOut("Example tree.shared(groups=A-B-C, calc=jabund-sorabund).\n"); + m->mothurOut("The default value for groups is all the groups in your groupfile.\n"); + m->mothurOut("The default value for calc is jclass-thetayc.\n"); + m->mothurOut("The tree.shared command outputs a .tre file for each calculator you specify at each distance you choose.\n"); validCalculator->printCalc("treegroup", cout); - mothurOut("Or the tree.shared command can be in the following format: tree.shared(phylip=yourPhylipFile).\n"); - mothurOut("Example tree.shared(phylip=abrecovery.dist).\n"); - mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); + m->mothurOut("Or the tree.shared command can be in the following format: tree.shared(phylip=yourPhylipFile).\n"); + m->mothurOut("Example tree.shared(phylip=abrecovery.dist).\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "help"); + m->errorOut(e, "TreeGroupCommand", "help"); exit(1); } } @@ -223,6 +275,7 @@ void TreeGroupCommand::help(){ //********************************************************************************************************************** TreeGroupCommand::~TreeGroupCommand(){ + globaldata->Groups.clear(); if (abort == false) { if (format == "sharedfile") { delete read; delete input; globaldata->ginput = NULL; } @@ -242,8 +295,9 @@ int TreeGroupCommand::execute(){ if (format == "sharedfile") { //if the users entered no valid calculators don't execute command - if (treeCalculators.size() == 0) { mothurOut("You have given no valid calculators."); mothurOutEndLine(); return 0; } - + if (treeCalculators.size() == 0) { m->mothurOut("You have given no valid calculators."); m->mothurOutEndLine(); return 0; } + + if (globaldata->gGroupmap != NULL) { delete globaldata->gGroupmap; globaldata->gGroupmap = NULL; } //you have groups read = new ReadOTUFile(globaldata->inputFileName); read->read(&*globaldata); @@ -252,13 +306,28 @@ int TreeGroupCommand::execute(){ lookup = input->getSharedRAbundVectors(); lastLabel = lookup[0]->getLabel(); - if (lookup.size() < 2) { mothurOut("You have not provided enough valid groups. I cannot run the command."); mothurOutEndLine(); return 0; } + if (lookup.size() < 2) { m->mothurOut("You have not provided enough valid groups. I cannot run the command."); m->mothurOutEndLine(); return 0; } //used in tree constructor globaldata->runParse = false; + //create treemap class from groupmap for tree class to use + tmap = new TreeMap(); + tmap->makeSim(globaldata->gGroupmap); + globaldata->gTreemap = tmap; + + //clear globaldatas old tree names if any + globaldata->Treenames.clear(); + + //fills globaldatas tree names + globaldata->Treenames = globaldata->Groups; + + if (m->control_pressed) { return 0; } + //create tree file makeSimsShared(); + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } }else{ //read in dist file filename = globaldata->inputFileName; @@ -282,6 +351,9 @@ int TreeGroupCommand::execute(){ //make treemap tmap = new TreeMap(); + + if (m->control_pressed) { return 0; } + tmap->makeSim(list); globaldata->gTreemap = tmap; @@ -296,28 +368,42 @@ int TreeGroupCommand::execute(){ //used in tree constructor globaldata->runParse = false; + if (m->control_pressed) { return 0; } + makeSimsDist(); + + if (m->control_pressed) { return 0; } //create a new filename - outputFile = outputDir + getRootName(getSimpleName(globaldata->inputFileName)) + "tre"; + outputFile = outputDir + m->getRootName(m->getSimpleName(globaldata->inputFileName)) + "tre"; + outputNames.push_back(outputFile); outputTypes["tree"].push_back(outputFile); createTree(); - mothurOut("Tree complete. "); mothurOutEndLine(); + + if (m->control_pressed) { return 0; } + + m->mothurOut("Tree complete. "); m->mothurOutEndLine(); + } //reset groups parameter globaldata->Groups.clear(); + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); return 0; } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "execute"); + m->errorOut(e, "TreeGroupCommand", "execute"); exit(1); } } //********************************************************************************************************************** -void TreeGroupCommand::createTree(){ +int TreeGroupCommand::createTree(){ try { //create tree t = new Tree(); @@ -326,7 +412,9 @@ void TreeGroupCommand::createTree(){ //there are numGroups - 1 merges to do for (int i = 0; i < (numGroups - 1); i++) { float largest = -1000.0; - + + if (m->control_pressed) { delete t; return 1; } + int row, column; //find largest value in sims matrix by searching lower triangle for (int j = 1; j < simMatrix.size(); j++) { @@ -380,15 +468,21 @@ void TreeGroupCommand::createTree(){ //assemble tree t->assembleTree(); + if (m->control_pressed) { delete t; return 1; } + //print newick file t->createNewickFile(outputFile); //delete tree delete t; + + if (m->control_pressed) { remove(outputFile.c_str()); outputNames.pop_back(); return 1; } + + return 0; } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "createTree"); + m->errorOut(e, "TreeGroupCommand", "createTree"); exit(1); } } @@ -412,12 +506,12 @@ void TreeGroupCommand::printSims(ostream& out) { } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "printSims"); + m->errorOut(e, "TreeGroupCommand", "printSims"); exit(1); } } /***********************************************************/ -void TreeGroupCommand::makeSimsDist() { +int TreeGroupCommand::makeSimsDist() { try { numGroups = list->size(); @@ -428,9 +522,9 @@ void TreeGroupCommand::makeSimsDist() { //initialize simMatrix simMatrix.clear(); simMatrix.resize(numGroups); - for (int m = 0; m < simMatrix.size(); m++) { + for (int k = 0; k < simMatrix.size(); k++) { for (int j = 0; j < simMatrix.size(); j++) { - simMatrix[m].push_back(0.0); + simMatrix[k].push_back(0.0); } } @@ -439,53 +533,45 @@ void TreeGroupCommand::makeSimsDist() { for(MatData currentCell = matrix->begin(); currentCell != matrix->end(); currentCell++){ //similairity = -(distance-1) simMatrix[currentCell->row][currentCell->column] = -(currentCell->dist -1.0); - simMatrix[currentCell->column][currentCell->row] = -(currentCell->dist -1.0); + simMatrix[currentCell->column][currentCell->row] = -(currentCell->dist -1.0); + + if (m->control_pressed) { return 1; } + } - + return 0; } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "makeSimsDist"); + m->errorOut(e, "TreeGroupCommand", "makeSimsDist"); exit(1); } } /***********************************************************/ -void TreeGroupCommand::makeSimsShared() { +int TreeGroupCommand::makeSimsShared() { try { - - //clear globaldatas old tree names if any - globaldata->Treenames.clear(); - - //fills globaldatas tree names - globaldata->Treenames = globaldata->Groups; - - //create treemap class from groupmap for tree class to use - tmap = new TreeMap(); - tmap->makeSim(globaldata->gGroupmap); - globaldata->gTreemap = tmap; - set processedLabels; set userLabels = labels; //as long as you are not at the end of the file or done wih the lines you want while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for(int i = 0 ; i < treeCalculators.size(); i++) { delete treeCalculators[i]; } return 1; } if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ - mothurOut(lookup[0]->getLabel()); mothurOutEndLine(); + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); process(lookup); processedLabels.insert(lookup[0]->getLabel()); userLabels.erase(lookup[0]->getLabel()); } - if ((anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = lookup[0]->getLabel(); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } lookup = input->getSharedRAbundVectors(lastLabel); - mothurOut(lookup[0]->getLabel()); mothurOutEndLine(); + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); process(lookup); processedLabels.insert(lookup[0]->getLabel()); @@ -502,16 +588,18 @@ void TreeGroupCommand::makeSimsShared() { lookup = input->getSharedRAbundVectors(); } + if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for(int i = 0 ; i < treeCalculators.size(); i++) { delete treeCalculators[i]; } return 1; } + //output error messages about any remaining user labels set::iterator it; bool needToRun = false; for (it = userLabels.begin(); it != userLabels.end(); it++) { - mothurOut("Your file does not include the label " + *it); + m->mothurOut("Your file does not include the label " + *it); if (processedLabels.count(lastLabel) != 1) { - mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } @@ -520,21 +608,23 @@ void TreeGroupCommand::makeSimsShared() { for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } } lookup = input->getSharedRAbundVectors(lastLabel); - mothurOut(lookup[0]->getLabel()); mothurOutEndLine(); + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); process(lookup); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } } for(int i = 0 ; i < treeCalculators.size(); i++) { delete treeCalculators[i]; } + + return 0; } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "makeSimsShared"); + m->errorOut(e, "TreeGroupCommand", "makeSimsShared"); exit(1); } } /***********************************************************/ -void TreeGroupCommand::process(vector thisLookup) { +int TreeGroupCommand::process(vector thisLookup) { try{ EstOutput data; vector subset; @@ -545,9 +635,9 @@ void TreeGroupCommand::process(vector thisLookup) { //initialize simMatrix simMatrix.clear(); simMatrix.resize(numGroups); - for (int m = 0; m < simMatrix.size(); m++) { + for (int k = 0; k < simMatrix.size(); k++) { for (int j = 0; j < simMatrix.size(); j++) { - simMatrix[m].push_back(0.0); + simMatrix[k].push_back(0.0); } } @@ -556,7 +646,8 @@ void TreeGroupCommand::process(vector thisLookup) { for (int g = 0; g < numGroups; g++) { index[g] = g; } //create a new filename - outputFile = outputDir + getRootName(getSimpleName(globaldata->inputFileName)) + treeCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + ".tre"; + outputFile = outputDir + m->getRootName(m->getSimpleName(globaldata->inputFileName)) + treeCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + ".tre"; + outputNames.push_back(outputFile); outputTypes["tree"].push_back(outputFile); for (int k = 0; k < thisLookup.size(); k++) { for (int l = k; l < thisLookup.size(); l++) { @@ -568,20 +659,43 @@ void TreeGroupCommand::process(vector thisLookup) { subset.push_back(thisLookup[k]); subset.push_back(thisLookup[l]); data = treeCalculators[i]->getValues(subset); //saves the calculator outputs + //cout << thisLookup[k]->getGroup() << '\t' << thisLookup[l]->getGroup() << '\t' << (1.0 - data[0]) << endl; + if (m->control_pressed) { return 1; } + //save values in similarity matrix simMatrix[k][l] = data[0]; simMatrix[l][k] = data[0]; } } } - + + //createdistance file from simMatrix + /*string o = outputDir + m->getRootName(m->getSimpleName(globaldata->inputFileName)) + treeCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + ".dist"; + ofstream outDist; + m->openOutputFile(o, outDist); + outDist << simMatrix.size() << endl; + for (int k = 0; k < simMatrix.size(); k++) { + outDist << thisLookup[k]->getGroup() << '\t'; + for (int l = 0; l < k; l++) { + outDist << (1.0-simMatrix[k][l]) << '\t'; + } + outDist << endl; + } + outDist.close();*/ + + + if (m->control_pressed) { return 1; } //creates tree from similarity matrix and write out file createTree(); + + if (m->control_pressed) { return 1; } } + + return 0; } catch(exception& e) { - errorOut(e, "TreeGroupCommand", "process"); + m->errorOut(e, "TreeGroupCommand", "process"); exit(1); } }